9e75f44f1a
Source-only snapshot of the cluster branch for WES execution. Large reference files (HPA/MANE/ensemble FASTA, model weights, ~597 MB) are omitted: they are baked into the container images at build time and mounted from the dreamdock-data PVC at runtime, and exceed the Gitea request size limit. Pipeline entry point is main.nf, which orchestrates the biotransformer, conplex and tissue modules as a single workflow. Ligand inputs are read from the eureka workspace; protein_zarr and chembl_db come from the dreamdock-data PVC.
54 lines
1.4 KiB
YAML
54 lines
1.4 KiB
YAML
apiVersion: batch/v1
|
|
kind: Job
|
|
metadata:
|
|
name: job-data-copy-digital-trials-node-to-pvc
|
|
namespace: bioinformatics
|
|
spec:
|
|
backoffLimit: 6
|
|
completionMode: NonIndexed
|
|
completions: 1
|
|
manualSelector: false
|
|
parallelism: 1
|
|
suspend: false
|
|
template:
|
|
spec:
|
|
containers:
|
|
- args:
|
|
- |
|
|
apk add --no-cache rsync
|
|
mkdir -p /target
|
|
rsync -av --exclude .git/ --exclude .git-old/ --exclude work/ /source/ /target/digital_trials/
|
|
command:
|
|
- /bin/sh
|
|
- -c
|
|
image: alpine
|
|
imagePullPolicy: Always
|
|
name: data-copy
|
|
resources: {}
|
|
terminationMessagePath: /dev/termination-log
|
|
terminationMessagePolicy: File
|
|
volumeMounts:
|
|
- mountPath: /source
|
|
name: k8s-node
|
|
- mountPath: /target
|
|
name: pvc-volume
|
|
dnsPolicy: ClusterFirst
|
|
nodeSelector:
|
|
kubernetes.io/hostname: k8s-node23
|
|
restartPolicy: Never
|
|
schedulerName: default-scheduler
|
|
securityContext: {}
|
|
terminationGracePeriodSeconds: 30
|
|
tolerations:
|
|
- effect: NoExecute
|
|
key: omic-app
|
|
operator: Equal
|
|
value: similarity-search
|
|
volumes:
|
|
- name: pvc-volume
|
|
persistentVolumeClaim:
|
|
claimName: dreamdock-data
|
|
- hostPath:
|
|
path: /data/bugra/digital_trials ## CHANGE ME
|
|
type: ""
|
|
name: k8s-node |